从论文到代码完成 RoIPooling
RoI Pooling
得到特征图和候选框，就会将候选框投影在特征图，然后停止一次缩放得到大小分歧的特征图，在 Faster RCNN 中，区域候选框用来预测对象是前景还是背景，这是 class head 要做的工作，而 regression 是学习到基于 anchor 的差分，也就是中心的偏移量和宽高的缩放。
【从论文到代码完成 RoIPooling】在投影过程中候选框的尺寸和位置是相关于输入图像，而不是相关于特征图，首先需求将其停止转换到候选框在特征图上详细位置，然后在对提取候选框停止尺寸的缩放。
给定一个特征图和一组提议，返回汇合的特征表示。区域提议网络被用来预测对象性和回归盒的偏向（对锚点）。这些偏移量与 anchor 分离起来生成候选框。这些倡议通常是输入图像的大小而不是特征层的大小。因而，这些倡议需求按比例减少到特征图层，之所以这样做，以便下游的CNN层可以提取特征。
我们在原图上有一个尺寸，也就是候选框中心点的坐标以及宽度，首先我们投影在原图上坐标点除以下采样的倍数，也就是 32 倍下采样，假如坐标无法整除则停止取整操作。
import numpy as np
import torch
import torch.nn as nn
floattype = torch.cuda.FloatTensor
class TorchROIPool(object):
def __init__(self, output_size, scaling_factor):
#输出特征图的尺寸
self.output_size = output_size
#缩放比率
self.scaling_factor = scaling_factor
def _roi_pool(self, features):
"""
在给定的缩放提取特征图根底，返回固定大小的特征图
Args:
features (np.Array):
"""
# 特征图的通道数、高 和 宽
num_channels, h, w = features.shape# 计算步长
w_stride = w/self.output_size
h_stride = h/self.output_size
#
res = torch.zeros((num_channels, self.output_size, self.output_size))
res_idx = torch.zeros((num_channels, self.output_size, self.output_size))for i in range(self.output_size):
for j in range(self.output_size):# important to round the start and end, and then conver to int
#
w_start = int(np.floor(j*w_stride))
w_end = int(np.ceil((j+1)*w_stride))
h_start = int(np.floor(i*h_stride))
h_end = int(np.ceil((i+1)*h_stride))
# limiting start and end based on feature limits
#
w_start = min(max(w_start, 0), w)
w_end = min(max(w_end, 0), w)
h_start = min(max(h_start, 0), h)
h_end = min(max(h_end, 0), h)
patch = features[:, h_start: h_end, w_start: w_end]
max_val, max_idx = torch.max(patch.reshape(num_channels, -1), dim=1)
res[:, i, j] = max_val
res_idx[:, i, j] = max_idx
return res, res_idx
def __call__(self, feature_layer, proposals):
"""Given feature layers and a list of proposals, it returns pooled
respresentations of the proposals. Proposals are scaled by scaling factor
before pooling.
Args:
feature_layer (np.Array): 特征层尺寸
proposals (list of np.Array): 列表中每一个元素 Each element of the list represents a bounding
box as (w,y,w,h)
Returns:
np.Array: proposal 数量，通道数，输出特征图高度, self.output_size
"""
batch_size, num_channels, _, _ = feature_layer.shape
# first scale proposals based on self.scaling factor
scaled_proposals = torch.zeros_like(proposals)
# the rounding by torch.ceil is important for ROI pool
scaled_proposals[:, 0] = torch.ceil(proposals[:, 0] * self.scaling_factor)
scaled_proposals[:, 1] = torch.ceil(proposals[:, 1] * self.scaling_factor)
scaled_proposals[:, 2] = torch.ceil(proposals[:, 2] * self.scaling_factor)
scaled_proposals[:, 3] = torch.ceil(proposals[:, 3] * self.scaling_factor)
res = torch.zeros((len(proposals), num_channels, self.output_size,
self.output_size))
res_idx = torch.zeros((len(proposals), num_channels, self.output_size,
self.output_size))# 遍历候选框
for idx in range(len(proposals)):
#
proposal = scaled_proposals[idx]
# adding 1 to include the end indices from proposal
extracted_feat = feature_layer[0, :, proposal[1].to(dtype=torch.int8):proposal[3].to(dtype=torch.int8)+1, proposal[0].to(dtype=torch.int8):proposal[2].to(dtype=torch.int8)+1]
res[idx], res_idx[idx] = self._roi_pool(extracted_feat)
return res
推荐阅读
- Ruby正则表达式介绍和用法图解
- Ruby字符串用法详细图解
- Ruby XPath和XSLT开发实例
- Ruby套接字编程介绍和实战图解
- Ruby OOPs概念（面向对象编程）
- Ruby范围解释和用法
- Ruby数组介绍和用法图解
- Ruby LDAP开发实战和原理全解
- Ruby多线程编程用法全解